DVMCP

by gzuuus

17 stars
2.6k downloads
Not rated
GitHub

About

Decentralizes computational tool discovery and execution by bridging Nostr's Data Vending Machine ecosystem, enabling distributed service interactions through NIP-89 announcements and direct Nostr event requests.

Details

Author
gzuuus
Repository
gzuuus/dvmcp
GitHub stars
17
Downloads
2,593
License
MIT License
Categories
AI, Developer Tools, Search, Infrastructure
Tags
#integration

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name DVMCP
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @highlight/mcp-server

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Prerequisite: Ensure you have Bun installed.

You can run the packages directly using bunx without installing them:


bash

bun install -g @dvmcp/bridge @dvmcp/discovery

bun install

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "dvmcp": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

DVMCP: Data Vending Machine Context Protocol

DVMCP (Data Vending Machine Context Protocol) is a project that bridges the Model Context Protocol (MCP) with Nostr's Data Vending Machine (DVM) ecosystem. It enables AI and computational services running on MCP servers to be seamlessly discovered, accessed, and utilized via the decentralized Nostr network.

This integration combines MCP's standardized capability framework with Nostr's cryptographically secure and decentralized messaging, offering key advantages:

Discoverability: MCP servers and their capabilities can be found through the Nostr network without centralized registries.
Verifiability: Messages are cryptographically signed, ensuring authenticity and integrity.
Decentralization: No single point of failure for service discovery or communication.
Protocol Interoperability: Both MCP and DVMs leverage JSON-RPC patterns, facilitating smooth communication.

For a detailed technical specification, refer to the DVMCP Specification (2025-03-26).

Event Kinds

The following Nostr event kinds are defined and used within the DVMCP:

| Kind | Description |
| ----- | ------------------------------------- |
| 31316 | Server Announcement |
| 31317 | Tools List |
| 31318 | Resources List |
| 31319 | Prompts List |
| 25910 | Requests |
| 26910 | Responses |
| 21316 | Feedback/Notifications |
| 1059 | Encrypted Messages (NIP-59 Gift Wrap) |

Packages

This monorepo contains the following packages:

@dvmcp/bridge

The bridge implementation that connects MCP servers to Nostr's DVM ecosystem. Handles tool announcement, execution, and status updates.

@dvmcp/discovery

A MCP server/discovery service that aggregates MCP tools from DVMs and makes their tools available.

@dvmcp/commons

Shared utilities and components used across DVMCP packages.

Installation & Usage

Prerequisite: Ensure you have Bun installed.

Quick Start with Bunx (No Installation)

You can run the packages directly using bunx without installing them:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.